An efficient approach for detection and classification of cancer regions in cervical images using optimization based CNN classification approach

Cervical cancer can be cured if it is initially screened and giving timely treatment to the patients. This paper proposes an optimization technique for exposing and segmenting the cancer portion in cervical images using transform and windowing technique. The image processing steps are preprocessing, transformation, feature extraction, feature optimization, classification, and segmentation involved in the proposed work. Initially, Gabor transform is enforced on the cervical test image to modify the pixels associated with the spatial domain into multi-resolution domain. Subsequently, the parameters of the multi-level features are extracted from the Gabor transformed cervical image. Then, the extracted features are optimized using the Genetic Algorithm (GA), and the optimistic prominent part is classified by the Convolutional Neural Networks (CNN). Finally, the Finite Segmentation Algorithm (FSA) is used to detect and segment the cancer region in cervical images. The proposed GA based CNN classification method describes the effectual detection and classification of cervical cancer by the parameters such as sensitivity, specificity and accuracy. The experimental results are shown 99.37% of average sensitivity, 98.9% of average specificity and 99.21% of average accuracy, 97.8% of PPV, 91.8% of NPV, 96.8% of FPR and 90.4% of FNR.